Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4484 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6732. Min Act: -0.0000

Data Index: 753954 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6103. Min Act: -0.0000

Data Index: 293773 (The Pile)

Max Activating Token Index: 674

Text #2

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5496. Min Act: -0.0000

Data Index: 53774 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1799112 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5574. Min Act: -0.0000

Data Index: 888681 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5381. Min Act: -0.0000

Data Index: 63034 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1001439 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1942544 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1579763 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4531. Min Act: -0.0000

Data Index: 902887 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1578106 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1553557 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4327. Min Act: -0.0000

Data Index: 767650 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1047934 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1620425 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1709603 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1669225 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1265648 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1043368 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1323626 (The Pile)

Max Activating Token Index: 801